# LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator

arXiv: https://arxiv.org/abs/2512.10605 · HTML: https://mlsanity.com/paper/2512.10605/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 23 of its 25 references that are in the map.
- First posted on arXiv 11 Dec 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [ProgPrompt: Generating Situated Robot Task Plans using Large Language Models](https://mlsanity.com/paper/2209.11302/) (2022)
- [VLABench: A Large-Scale Benchmark for Language-Conditioned Robotics Manipulation with Long-Horizon Reasoning Tasks](https://mlsanity.com/paper/2412.18194/) (2024)
- [Task and Motion Planning with Large Language Models for Object Rearrangement](https://mlsanity.com/paper/2303.06247/) (2023)
- [Large Language Models for Robotics: A Survey](https://mlsanity.com/paper/2311.07226/) (2023)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [Chat with the Environment: Interactive Multimodal Perception Using Large Language Models](https://mlsanity.com/paper/2303.08268/) (2023)
- [CoPAL: Corrective Planning of Robot Actions with Large Language Models](https://mlsanity.com/paper/2310.07263/) (2023)
- [Deploying and Evaluating LLMs to Program Service Mobile Robots](https://mlsanity.com/paper/2311.11183/) (2023)
- [DisasterResponseGPT: Large Language Models for Accelerated Plan of Action Development in Disaster Response Scenarios](https://mlsanity.com/paper/2306.17271/) (2023)
- [Interactive Planning Using Large Language Models for Partially Observable Robotics Tasks](https://mlsanity.com/paper/2312.06876/) (2023)
- [In-Context Learning Enables Robot Action Prediction in LLMs](https://mlsanity.com/paper/2410.12782/) (2024)
- [TypeFly: Flying Drones with Large Language Model](https://mlsanity.com/paper/2312.14950/) (2023)
- [REAL: Resilience and Adaptation using Large Language Models on Autonomous Aerial Robots](https://mlsanity.com/paper/2311.01403/) (2023)
- [MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation](https://mlsanity.com/paper/2411.17636/) (2024)
- [Agent as Cerebrum, Controller as Cerebellum: Implementing an Embodied LMM-based Agent on Drones](https://mlsanity.com/paper/2311.15033/) (2023)
- [General-Purpose Aerial Intelligent Agents Empowered by Large Language Models](https://mlsanity.com/paper/2503.08302/) (2025)
- [MageBench: Bridging Large Multimodal Models to Agents](https://mlsanity.com/paper/2412.04531/) (2024)

## Abstract (arXiv)

We propose LEO-RobotAgent, a general-purpose language-driven intelligent agent framework for robots. Under this framework, LLMs can operate different types of robots to complete unpredictable complex tasks across various scenarios. This framework features strong generalization, robustness, and efficiency. The application-level system built around it can fully enhance bidirectional human-robot intent understanding and lower the threshold for human-robot interaction. Regarding robot task planning, the vast majority of existing studies focus on the application of large models in single-task scenarios and for single robot types. These algorithms often have complex structures and lack generalizability. Thus, the proposed LEO-RobotAgent framework is designed with a streamlined structure as much as possible, enabling large models to independently think, plan, and act within this clear framework. We provide a modular and easily registrable toolset, allowing large models to flexibly call various tools to meet different requirements. Meanwhile, the framework incorporates a human-robot interaction mechanism, enabling the algorithm to collaborate with humans like a partner. Experiments have verified that this framework can be easily adapted to mainstream robot platforms including unmanned aerial vehicles (UAVs), robotic arms, and wheeled robot, and efficiently execute a variety of carefully designed tasks with different complexity levels. Our code is available at https://github.com/LegendLeoChen/LEO-RobotAgent.